Abstract:Aiming at the difficulty of feature extraction in traditional mechanical fault diagnosis methods, a novel dynamic weighted multi-scale residual network rotating machine fault diagnosis method based on feature channel recalibration is proposed. Firstly, the raw data is taken as the input of the network, and a wide convolution layer is designed to preliminarily fuse the information and expand the receptive field of the model; Then three independent parallel branch networks based on residual blocks are constructed, and the depth features are extracted from the parallel branch networks by designing multi-scale convolution kernels; Next, a dynamic weighting layer is designed to model the dynamic nonlinear relationship between feature channels using global information, and recalibrate the feature channels of each scale to improve the sensitivity of the network to fault information. Finally, the features of the three scales are fused, and the fault diagnosis is realized by the classifier. Experiments on several datasets verify the effectiveness of the proposed algorithm.
Key words: Fault diagnosis of rotating machinery; Dynamic weighting; One-dimensional residual network; Multi-scale learning
史红梅,郑畅畅,司瑾,陈晶城. 基于动态加权的多尺度残差网络旋转机械故障诊断算法[J]. 振动与冲击, 2022, 41(23): 67-74.
SHI Hongmei, ZHENG Changchang, SI Jin, CHEN Jingcheng. Fault diagnosis algorithm of rotating machinery based on dynamic weighted multiscale residual network. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(23): 67-74.
[1] Wang Z, Wang J, Wang Y. An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition[J]. Neurocomputing, 2018, 310(OCT.8): 213-222.
[2] 刘恒畅, 姚德臣, 杨建伟,等. 基于多分支深度可分离卷积神经网络的滚动轴承故障诊断研究[J]. 振动与冲击, 40(10):8.
Liu H C, Yao D C, Yang J W, et al. Research on fault diagnosis of rolling bearings based on multi-branch depth separable convolutional neural network[J]. Vibration and Shock, 40(10):8.
[3] 雷亚国, 贾峰, 孔德同. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 054(005):94-104.
Lei Y G, Jia F, Kong D T, et al. Opportunities and Challenges of Machinery Intelligent Fault Diagnosis in Big Data Era[J]. Journal of Mechanical Engineering, 2018.
[4] Hu A, Yan X, Xiang L. A new wind turbine fault diagnosis method based on ensemble intrinsic time-scale decomposition and WPT-fractal dimension[J]. Renewable Energy, 2015, 83:767-778.
[5] Xu Y G, Zhao G L, Ma C Y, et al. Denoising method based on dual-tree complex wavelet transform and MCA and its application in gear fault diagnosis[J]. Journal of Aerospace Power, 2016.
[6] Li R, Se Kiner S U, He D, et al. Gear Fault Location Detection for Split Torque Gearbox Using AE Sensors[J]. IEEE Transactions on Systems Man & Cybernetics Part C, 2012, 42(6): 1308-1317.
[7] 周小龙, 刘薇娜, 姜振海,等. 改进的HHT方法及其在旋转机械故障诊断中的应用[J]. 振动与冲击, 2020, 39(7):189-195.
Zhou X L, Liu W N, Jiang Z H, et al. Improved HHT method and its application in fault diagnosis of rotating machinery[J]. Vibration and Shock, 2020, 39(7):189-195.
[8] Zhao Z, Li T, Wu J, et al. Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark Study[J]. arXiv preprint arXiv: 2003.03315, 2020.
[9] 姜洪开, 邵海东, 李兴球. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报, 2019, 55(007):27-34.
Jiang H K, Shao H D, Li X Q. Intelligent fault diagnosis method of aircraft based on deep learning [J]. Journal of Mechanical Engineering, 2019, 55(007):27-34.
[10] Wen L, Li X, Gao L, et al. A New Convolutional Neural Network Based Data-Driven Fault Diagnosis Method[J]. IEEE Transactions on Industrial Electronics, 2017, PP(99): 1-1.
[11] Han Y, Tang B, Deng L. An enhanced convolutional neural network with enlarged receptive fields for fault diagnosis of planetary gearboxes[J]. Computers in Industry, 2019, 107: 50-58.
[12] 赵光权, 葛强强, 刘小勇. 基于DBN的故障特征提取及诊断方法研究[J]. 仪器仪表学报, 2016, 37(009):1946-1953.
Zhao G Q, Ge Q, Liu X Y. Fault Feature Extraction and Diagnosis Method Based on Deep Belief network[J]. Chinese journal of scientific instrument, 2016, 37(009):1946-1953.
[13] Jiang, Guo Q, Hai B, et al. Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox[J]. IEEE Transactions on Industrial Electronics, 2019.
[14] Peng D, Liu Z, Wang H, et al. A Novel Deeper One-Dimensional CNN With Residual Learning for Fault Diagnosis of Wheelset Bearings in High-Speed Trains[J]. IEEE Access, 2018:10278-10293.
[15] 丁康, 朱小勇, 陈亚华. 齿轮箱典型故障振动特征与诊断策略[J]. 振动与冲击, 2001, 20(3): 7-12.
Ding K, Zhu X Y, Chen Y H. Vibration characteristics and diagnosis strategy of typical gearbox faults [J]. Vibration and Shock, 2001, 20(3): 7-12.
[16] He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]. //IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society, 2016.
[17] V. Nair and G. E. Hinton. Rectified linear units improve restricted boltzmann machines[C]. //Proceedings of the 27th international conference on machine learning (ICML-10), pp. 807–814, Jun. 2010.
[18] Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift[J]. 2015.
[19] Hu J, Shen L, Albanie S, et al. Squeeze-and-Excitation Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, PP (99).
[20] Lei Y, Jia F, Lin J, et al. An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data[J]. IEEE Transactions on Industrial Electronics, 2016, 63(5):3137-3147.
[21] Kingma D, Ba J. Adam: A Method for Stochastic Optimization[J]. Computer Science, 2014.
[22] L. v. d. Maaten, G. Hinton. Visualizing data using t-sne[J]. Journal of Machine Learning Research, vol. 9, pp. 2579–2605, Nov. 2008.